/cm-how-it-work

name: cm-how-it-work
description: "Complete guide to vibe coding with CodyMaster — from idea to deploy. Read this first if you are new."
disable-model-invocation: true

CodyMaster Kit — The Ultimate Vibe Coding Guide

Overview

The **CodyMaster (CM)** kit transforms ideas into production code through 13 specialized, optimized skills. This workflow ensures the highest quality, absolute security, and maximum execution speed.

💡 Idea → 🔍 Analysis → 📐 Design → 🧪 Test-first (TDD) → 💻 Code → ✅ Verify → 🚀 Deploy → 🔄 Iterate

---

Workflow

Phase 0: Identity & Safety 🔒

> **Rule #1:** Always verify identity before performing any action that could change the project state.

• **Skill:** `cm-identity-guard`
• **When:** At the start of a work session, before git push, deploy, or database operations.
• **Action:** Run `node check-identity.js` (or similar script) to verify GitHub/Cloudflare/Supabase accounts.

---

Phase 0.3: Knowledge Infrastructure Setup 🧠

> **For large codebases, establish the memory foundation before planning.**

• **Skills:** `cm-codeintell` + `cm-dockit` + `cm-deep-search` + `cm-notebooklm`
• **When:** When onboarding to a new codebase or starting a massive refactoring initiative.
• **Action:**

1. Scan structure with `cm-codeintell` to build the Skeleton Index. 2. Generate missing architectural docs with `cm-dockit`. 3. Index the docs for fast local retrieval with `cm-deep-search` (qmd). 4. Sync high-value patterns to the Cloud Brain with `cm-notebooklm`.

• **Output:** A fully indexed 5-tier memory ecosystem ready for precise, low-token AI problem solving.

---

Phase 0.5: Strategic Analysis 🔍

> **For complex initiatives and enhancements on existing products.**

• **Skills:** `cm-brainstorm-idea` + `cm-codeintell`
• **When:** When the task is complex and requires multi-dimensional analysis (tech, product, design, business) before planning.
• **Action:**

1. Scan codebase with **code intelligence** (AST graph + architecture diagram via `cm-codeintell`). 2. Interview user and analyze with 9 Windows (TRIZ). 3. Propose 2-3 options, evaluate multi-dimensionally, recommend the best option.

• **Output:** OpenSpec `openspec/changes/[initiative]/proposal.md` — qualified problem + recommended option → passes to `cm-planning`.

---

Phase 1: Planning & Design 📐

> **Understand the 'Job to be Done' (JTBD) and architecture before writing code.**

• **Skill:** `cm-planning` (Combines brainstorming + writing-plans)
• **Action:**

1. Brainstorm requirements and analyze i18n. 2. Propose architecture and tech stack. 3. Write detailed OpenSpec docs (`openspec/changes/[init]/design.md` and `tasks.md`).

• **Output:** Design docs and execution plan (OpenSpec tasks) approved by user.

---

Phase 2: Implementation (TDD & Execution) 💻

> **Turn the plan into actual source code safely.**

• **Skills:**
• `cm-tdd`: Red-Green-Refactor cycle. No production code without a failing test first.
• `cm-execution`: Execute plans intelligently (Manual, Parallel, or Subagent mode).
• `cm-project-bootstrap`: For new projects — setup repo, i18n, SEO, and deploy pipeline from Day 0.
• `cm-execution`: Isolate different work items to avoid state mixing.

---

Phase 3: Quality Control & Verification ✅

> **Prove with evidence, not words.**

• **Skills:**
• `cm-quality-gate`: Setup test infrastructure (`test:gate`) and verify output before claiming "done".
• `cm-debugging`: When tests fail, use systematic investigation framework to find root cause.
• `cm-code-review`: Professional request and feedback review process.

---

Phase 4: Safe Deployment 🚀

> **Ship code without fear of incidents.**

• **Skills:**
• `cm-safe-deploy`: Run 8-gate pipeline (Secret → Syntax → Test → Build → Deploy → Smoke).
• `cm-safe-i18n`: Translate and synchronize languages consistently across the entire project.
• `cm-terminal`: Monitor all terminal commands to detect errors immediately.

---

CodyMaster Kit — 34 Skills Summary

🔧 Engineering

| Skill | Primary Function | |-------|-----------------| | `cm-tdd` | Strict Red-Green-Refactor TDD — no code without failing test first. | | `cm-debugging` | Systematic 5-phase error investigation (root cause first). | | `cm-quality-gate` | 6-gate verification: static analysis → blind review → ship. | | `cm-quality-gate` | Setup and enforce the verification gate before claiming "done". | | `cm-code-review` | Manage PR lifecycle: request → receive feedback → complete branch. | | `cm-codeintell` | AST knowledge graph + architecture diagrams + smart context (30% fewer tokens). |

⚙️ Operations

| Skill | Primary Function | |-------|-----------------| | `cm-safe-deploy` | Multi-gate deploy pipeline with rollback strategy. | | `cm-identity-guard` | Verify account before push/deploy to prevent wrong-project incidents. | | `cm-execution` | Isolate feature work in separate workspaces/batches — no state mixing. | | `cm-terminal` | Safe terminal execution with progress logging and error capture. | | `cm-safe-deploy` | Defense-in-depth: pre-commit hooks, repo scanning, token lifecycle. | | `cm-safe-i18n` | Safe multi-language management with multi-pass batching and 8-gate audit. |

🎨 Product

| Skill | Primary Function | |-------|-----------------| | `cm-project-bootstrap` | Full project setup: design system → CI → staging → deploy from Day 0. | | `cm-brainstorm-idea` | Strategic analysis gate: 9 Windows + Double Diamond → 2-3 qualified options. | | `cm-planning` | Brainstorm intent → write implementation plan → coordinate execution. | | `cm-ux-master` | 48 UX Laws + 37 Design Tests + Figma/Stitch + BM25 semantic design search. | | `cm-design-system` | Live UI concept generation via design-token and Stitch/Open Design workflows. | | `cm-dockit` | Generate complete knowledge bases, SOPs, and API docs from codebase. | | `cm-readit` | Web audio engine: TTS reader, MP3 a